ClawHub
Back to skill

Security audit

ChatBotKit

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed ChatBotKit connector that can read and change ChatBotKit resources through the scoped OOMOL `oo` CLI, with user confirmation required for writes.

Install this only if you intend to let an agent use your OOMOL-connected ChatBotKit account. Review write actions carefully before approval, especially creating or updating bots, datasets, conversations, records, files, and uploads; read-only listing and fetching actions are lower risk.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill description says to use this skill for ANY ChatBotKit request and instead of calling the API directly, which is an overly broad trigger that can cause the agent to invoke the skill in situations where a narrower or safer path would be more appropriate. Overbroad routing increases the chance of unintended tool use, including state-changing operations, especially because this same skill exposes both read and write actions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.